Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to expectations and their evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سكانية
    -0.53
     mergeFrom
    -0.52
    ing
    -0.52
    Portail
    -0.49
    __*/
    -0.47
    ismet
    -0.47
    }{*}{
    -0.45
    ölkerung
    -0.45
    ┘
    -0.45
     kiệm
    -0.44
    POSITIVE LOGITS
    ffions
    0.85
    TagHelpers
    0.81
     forth
    0.78
    ftance
    0.78
    noopener
    0.75
    AutoScale
    0.75
    еремо
    0.75
    \<^
    0.74
    iffance
    0.72
     springfox
    0.72
    Act Density 0.709%

    No Known Activations